Skip to content

Fix CRLF line positions after reading records #433

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
onuracar-dev wants to merge 1 commit into
base: master
Choose a base branch
from
+129 −13
Open

Fix CRLF line positions after reading records #433

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
126 changes: 113 additions & 13 deletions csv-core/src/reader.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -126,6 +126,8 @@ pub struct Reader {
has_read: bool,
/// The current position in the output buffer when reading a record.
output_pos: usize,
/// Whether a record ended with `\r` at the end of the input buffer.
pending_crlf_record: bool,
}

impl Default for Reader {
Expand All @@ -145,6 +147,7 @@ impl Default for Reader {
line: 1,
has_read: false,
output_pos: 0,
pending_crlf_record: false,
}
}
}
Expand Down Expand Up @@ -485,6 +488,7 @@ impl Reader {
self.line = 1;
self.has_read = false;
self.output_pos = 0;
self.pending_crlf_record = false;
}

/// Return the current line number as measured by the number of occurrences
Expand Down Expand Up @@ -595,6 +599,19 @@ impl Reader {
ends: &mut [usize],
) -> (ReadRecordResult, usize, usize, usize) {
let (input, bom_nin) = self.strip_utf8_bom(input);
if self.pending_crlf_record {
self.pending_crlf_record = false;
self.output_pos = 0;
if self.use_nfa {
self.nfa_state = NfaState::StartRecord;
} else {
self.dfa_state = self.dfa.new_state(NfaState::StartRecord);
}
let nin = usize::from(input.first() == Some(&b'\n'));
self.line += nin as u64;
self.has_read = true;
return (ReadRecordResult::Record, nin + bom_nin, 0, 0);
}
let (res, nin, nout, nend) = if self.use_nfa {
self.read_record_nfa(input, output, ends)
} else {
Expand Down Expand Up @@ -660,6 +677,8 @@ impl Reader {
}
let (mut nin, mut nout, mut nend) = (0, 0, 0);
let mut state = self.dfa_state;
let crlf = self.dfa.new_state(NfaState::CRLF);
let mut completed_crlf = false;
while nin < input.len() && nout < output.len() && nend < ends.len() {
let (s, has_out) = self.dfa.get_output(state, input[nin]);
self.line += (input[nin] == b'\n') as u64;
Expand All @@ -669,6 +688,21 @@ impl Reader {
nout += 1;
}
nin += 1;
if state == crlf {
ends[nend] = self.output_pos + nout;
nend += 1;
if nin < input.len() {
if input[nin] == b'\n' {
self.line += 1;
nin += 1;
}
state = self.dfa.new_state(NfaState::StartRecord);
completed_crlf = true;
} else {
self.pending_crlf_record = true;
}
break;
}
if state >= self.dfa.final_field {
ends[nend] = self.output_pos + nout;
nend += 1;
Expand All @@ -682,13 +716,19 @@ impl Reader {
.scan_and_copy(input, &mut nin, output, &mut nout);
}
}
let res = self.dfa.new_read_record_result(
state,
false,
nin >= input.len(),
nout >= output.len(),
nend >= ends.len(),
);
let res = if completed_crlf {
ReadRecordResult::Record
} else if self.pending_crlf_record {
ReadRecordResult::InputEmpty
} else {
self.dfa.new_read_record_result(
state,
false,
nin >= input.len(),
nout >= output.len(),
nend >= ends.len(),
)
};
self.dfa_state = state;
if res.is_record() {
self.output_pos = 0;
Expand Down Expand Up @@ -879,6 +919,7 @@ impl Reader {
}
let (mut nin, mut nout, mut nend) = (0, self.output_pos, 0);
let mut state = self.nfa_state;
let mut completed_crlf = false;
while nin < input.len() && nout < output.len() && nend < ends.len() {
let (s, io) = self.transition_nfa(state, input[nin]);
match io {
Expand All @@ -893,6 +934,21 @@ impl Reader {
NfaInputAction::Epsilon => {}
}
state = s;
if state == NfaState::CRLF {
ends[nend] = nout;
nend += 1;
if nin < input.len() {
if input[nin] == b'\n' {
self.line += 1;
nin += 1;
}
state = NfaState::StartRecord;
completed_crlf = true;
} else {
self.pending_crlf_record = true;
}
break;
}
if state.is_field_final() {
ends[nend] = nout;
nend += 1;
Expand All @@ -901,12 +957,18 @@ impl Reader {
}
}
}
let res = ReadRecordResult::from_nfa(
state,
nin >= input.len(),
nout >= output.len(),
nend >= ends.len(),
);
let res = if completed_crlf {
ReadRecordResult::Record
} else if self.pending_crlf_record {
ReadRecordResult::InputEmpty
} else {
ReadRecordResult::from_nfa(
state,
nin >= input.len(),
nout >= output.len(),
nend >= ends.len(),
)
};
self.nfa_state = state;
self.output_pos = if res.is_record() { 0 } else { nout };
(res, nin, nout, nend)
Expand Down Expand Up @@ -1972,6 +2034,44 @@ mod tests {
assert_read_record!(rdr, &inp, out, ends, 0, 0, 0, End);
}

#[test]
fn stream_record_with_crlf() {
use crate::ReadRecordResult::*;

let out = &mut [0; 1024];
let ends = &mut [0; 10];
let mut rdr = Reader::new();

assert_eq!(rdr.line(), 1);
assert_read_record!(rdr, b("foo,bar\r\n"), out, ends, 9, 6, 2, Record);
assert_eq!(&ends[..2], &[3, 6]);
assert_eq!(rdr.line(), 2);
}

#[test]
fn stream_record_with_split_crlf() {
use crate::ReadRecordResult::*;

let out = &mut [0; 1024];
let ends = &mut [0; 10];
let mut rdr = Reader::new();

assert_read_record!(
rdr,
b("foo,bar\r"),
out,
ends,
8,
6,
2,
InputEmpty
);
assert_eq!(rdr.line(), 1);

assert_read_record!(rdr, b("\n"), out, ends, 1, 0, 0, Record);
assert_eq!(rdr.line(), 2);
}

// Test that if our output ends are full during the last read that
// we get an appropriate state returned.
#[test]
Expand Down
16 changes: 16 additions & 0 deletions src/reader.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2597,6 +2597,22 @@ mod tests {
assert_eq!(pos.record(), 1);
}

#[test]
fn positions_crlf() {
let mut rdr = ReaderBuilder::new()
.has_headers(false)
.from_reader(b("a,b\r\nc,d\r\n"));
let mut record = StringRecord::new();

assert!(rdr.read_record(&mut record).unwrap());
assert_eq!(record.position().unwrap().line(), 1);
assert_eq!(rdr.position().line(), 2);

assert!(rdr.read_record(&mut record).unwrap());
assert_eq!(record.position().unwrap().line(), 2);
assert_eq!(rdr.position().line(), 3);
}

// Test that position info is reported correctly with headers.
#[test]
fn positions_headers() {
Expand Down
Loading